ElevenLabs

Package: elevenlabs · 16 nodes · Text-to-speech, speech-to-speech, sound effects, and voice management

Generate natural-sounding voice audio from text, clone voices, convert speech-to-speech, create sound effects, and manage voices via the ElevenLabs API.

Node Reference

Node	Type	Inputs	Outputs
Create Client	statement	API Key (str)	Client (elevenlabs.Client)
Set Api Key	statement	API Key (str)	-
Voice Id	expression	-	Voice ID (str)
Model Id	expression	-	Model ID (str)
Output Format	expression	-	Format (str)
Voice Settings	expression	-	Settings JSON (str)
Generate	statement	Client (elevenlabs.Client), Text (str), Voice ID (str), Model ID (str), Output Format (str)	Audio (elevenlabs.Audio)
Stream	statement	Client (elevenlabs.Client), Text (str), Voice ID (str), Model ID (str)	Audio Stream (elevenlabs.Audio)
Speech To Speech	statement	Client (elevenlabs.Client), Audio Path (str), Voice ID (str), Model ID (str)	Audio (elevenlabs.Audio)
Sound Effects	statement	Client (elevenlabs.Client), Description (str)	Audio (elevenlabs.Audio)
Audio Isolation	statement	Client (elevenlabs.Client), Audio Path (str)	Clean Audio (elevenlabs.Audio)
Save Audio	statement	Audio (elevenlabs.Audio), File Path (str)	File Path (str)
Play Audio	statement	Audio (elevenlabs.Audio)	-
List Voices	statement	Client (elevenlabs.Client)	Voices (any)
Get Voice	statement	Client (elevenlabs.Client), Voice ID (str)	Voice (elevenlabs.Voice), Name (str)
Clone Voice	statement	Client (elevenlabs.Client), Voice Name (str), Audio Path (str)	Voice ID (str), Voice (elevenlabs.Voice)

Typical Pipeline

Create Client → Generate (with Voice Id + Model Id) → Save Audio / Play Audio.

For voice cloning: Create Client → Clone Voice → Generate with cloned Voice ID.

For sound effects: Create Client → Sound Effects (describe the sound) → Save Audio.